#!/usr/bin/env python
# -*- encoding: utf-8 -*-
#
# This file is auto-generated by h2o-3/h2o-bindings/bin/gen_python.py
# Copyright 2016 H2O.ai; Apache License Version 2.0 (see LICENSE for details)
#
from h2o.utils.metaclass import deprecated_params, deprecated_property
import h2o
from h2o.utils.typechecks import U
from h2o.exceptions import H2OValueError
from h2o.estimators.estimator_base import H2OEstimator
from h2o.exceptions import H2OValueError
from h2o.frame import H2OFrame
from h2o.utils.typechecks import assert_is_type, Enum, numeric
[docs]class H2OGeneralizedAdditiveEstimator(H2OEstimator):
"""
Generalized Additive Model
Fits a generalized additive model, specified by a response variable, a set of predictors, and a
description of the error distribution.
A subclass of :class:`ModelBase` is returned. The specific subclass depends on the machine learning task
at hand (if it's binomial classification, then an H2OBinomialModel is returned, if it's regression then a
H2ORegressionModel is returned). The default print-out of the models is shown, but further GAM-specific
information can be queried out of the object. Upon completion of the GAM, the resulting object has
coefficients, normalized coefficients, residual/null deviance, aic, and a host of model metrics including
MSE, AUC (for logistic regression), degrees of freedom, and confusion matrices.
"""
algo = "gam"
supervised_learning = True
_options_ = {'model_extensions': ['h2o.model.extensions.ScoringHistoryGLM',
'h2o.model.extensions.Fairness']}
@deprecated_params({'Lambda': 'lambda_'})
def __init__(self,
model_id=None, # type: Optional[Union[None, str, H2OEstimator]]
training_frame=None, # type: Optional[Union[None, str, H2OFrame]]
validation_frame=None, # type: Optional[Union[None, str, H2OFrame]]
nfolds=0, # type: int
seed=-1, # type: int
keep_cross_validation_models=True, # type: bool
keep_cross_validation_predictions=False, # type: bool
keep_cross_validation_fold_assignment=False, # type: bool
fold_assignment="auto", # type: Literal["auto", "random", "modulo", "stratified"]
fold_column=None, # type: Optional[str]
response_column=None, # type: Optional[str]
ignored_columns=None, # type: Optional[List[str]]
ignore_const_cols=True, # type: bool
score_each_iteration=False, # type: bool
offset_column=None, # type: Optional[str]
weights_column=None, # type: Optional[str]
family="auto", # type: Literal["auto", "gaussian", "binomial", "quasibinomial", "ordinal", "multinomial", "poisson", "gamma", "tweedie", "negativebinomial", "fractionalbinomial"]
tweedie_variance_power=0.0, # type: float
tweedie_link_power=0.0, # type: float
theta=0.0, # type: float
solver="auto", # type: Literal["auto", "irlsm", "l_bfgs", "coordinate_descent_naive", "coordinate_descent", "gradient_descent_lh", "gradient_descent_sqerr"]
alpha=None, # type: Optional[List[float]]
lambda_=None, # type: Optional[List[float]]
lambda_search=False, # type: bool
early_stopping=True, # type: bool
nlambdas=-1, # type: int
standardize=False, # type: bool
missing_values_handling="mean_imputation", # type: Literal["mean_imputation", "skip", "plug_values"]
plug_values=None, # type: Optional[Union[None, str, H2OFrame]]
compute_p_values=False, # type: bool
remove_collinear_columns=False, # type: bool
splines_non_negative=None, # type: Optional[List[bool]]
intercept=True, # type: bool
non_negative=False, # type: bool
max_iterations=-1, # type: int
objective_epsilon=-1.0, # type: float
beta_epsilon=0.0001, # type: float
gradient_epsilon=-1.0, # type: float
link="family_default", # type: Literal["family_default", "identity", "logit", "log", "inverse", "tweedie", "ologit"]
startval=None, # type: Optional[List[float]]
prior=-1.0, # type: float
cold_start=False, # type: bool
lambda_min_ratio=-1.0, # type: float
beta_constraints=None, # type: Optional[Union[None, str, H2OFrame]]
max_active_predictors=-1, # type: int
interactions=None, # type: Optional[List[str]]
interaction_pairs=None, # type: Optional[List[tuple]]
obj_reg=-1.0, # type: float
export_checkpoints_dir=None, # type: Optional[str]
stopping_rounds=0, # type: int
stopping_metric="auto", # type: Literal["auto", "deviance", "logloss", "mse", "rmse", "mae", "rmsle", "auc", "aucpr", "lift_top_group", "misclassification", "mean_per_class_error", "custom", "custom_increasing"]
stopping_tolerance=0.001, # type: float
balance_classes=False, # type: bool
class_sampling_factors=None, # type: Optional[List[float]]
max_after_balance_size=5.0, # type: float
max_confusion_matrix_size=20, # type: int
max_runtime_secs=0.0, # type: float
num_knots=None, # type: Optional[List[int]]
spline_orders=None, # type: Optional[List[int]]
knot_ids=None, # type: Optional[List[str]]
gam_columns=None, # type: Optional[List[List[str]]]
standardize_tp_gam_cols=False, # type: bool
scale_tp_penalty_mat=False, # type: bool
bs=None, # type: Optional[List[int]]
scale=None, # type: Optional[List[float]]
keep_gam_cols=False, # type: bool
store_knot_locations=False, # type: bool
auc_type="auto", # type: Literal["auto", "none", "macro_ovr", "weighted_ovr", "macro_ovo", "weighted_ovo"]
gainslift_bins=-1, # type: int
):
"""
:param model_id: Destination id for this model; auto-generated if not specified.
Defaults to ``None``.
:type model_id: Union[None, str, H2OEstimator], optional
:param training_frame: Id of the training data frame.
Defaults to ``None``.
:type training_frame: Union[None, str, H2OFrame], optional
:param validation_frame: Id of the validation data frame.
Defaults to ``None``.
:type validation_frame: Union[None, str, H2OFrame], optional
:param nfolds: Number of folds for K-fold cross-validation (0 to disable or >= 2).
Defaults to ``0``.
:type nfolds: int
:param seed: Seed for pseudo random number generator (if applicable)
Defaults to ``-1``.
:type seed: int
:param keep_cross_validation_models: Whether to keep the cross-validation models.
Defaults to ``True``.
:type keep_cross_validation_models: bool
:param keep_cross_validation_predictions: Whether to keep the predictions of the cross-validation models.
Defaults to ``False``.
:type keep_cross_validation_predictions: bool
:param keep_cross_validation_fold_assignment: Whether to keep the cross-validation fold assignment.
Defaults to ``False``.
:type keep_cross_validation_fold_assignment: bool
:param fold_assignment: Cross-validation fold assignment scheme, if fold_column is not specified. The
'Stratified' option will stratify the folds based on the response variable, for classification problems.
Defaults to ``"auto"``.
:type fold_assignment: Literal["auto", "random", "modulo", "stratified"]
:param fold_column: Column with cross-validation fold index assignment per observation.
Defaults to ``None``.
:type fold_column: str, optional
:param response_column: Response variable column.
Defaults to ``None``.
:type response_column: str, optional
:param ignored_columns: Names of columns to ignore for training.
Defaults to ``None``.
:type ignored_columns: List[str], optional
:param ignore_const_cols: Ignore constant columns.
Defaults to ``True``.
:type ignore_const_cols: bool
:param score_each_iteration: Whether to score during each iteration of model training.
Defaults to ``False``.
:type score_each_iteration: bool
:param offset_column: Offset column. This will be added to the combination of columns before applying the link
function.
Defaults to ``None``.
:type offset_column: str, optional
:param weights_column: Column with observation weights. Giving some observation a weight of zero is equivalent
to excluding it from the dataset; giving an observation a relative weight of 2 is equivalent to repeating
that row twice. Negative weights are not allowed. Note: Weights are per-row observation weights and do
not increase the size of the data frame. This is typically the number of times a row is repeated, but
non-integer values are supported as well. During training, rows with higher weights matter more, due to
the larger loss function pre-factor. If you set weight = 0 for a row, the returned prediction frame at
that row is zero and this is incorrect. To get an accurate prediction, remove all rows with weight == 0.
Defaults to ``None``.
:type weights_column: str, optional
:param family: Family. Use binomial for classification with logistic regression, others are for regression
problems.
Defaults to ``"auto"``.
:type family: Literal["auto", "gaussian", "binomial", "quasibinomial", "ordinal", "multinomial", "poisson", "gamma",
"tweedie", "negativebinomial", "fractionalbinomial"]
:param tweedie_variance_power: Tweedie variance power
Defaults to ``0.0``.
:type tweedie_variance_power: float
:param tweedie_link_power: Tweedie link power
Defaults to ``0.0``.
:type tweedie_link_power: float
:param theta: Theta
Defaults to ``0.0``.
:type theta: float
:param solver: AUTO will set the solver based on given data and the other parameters. IRLSM is fast on on
problems with small number of predictors and for lambda-search with L1 penalty, L_BFGS scales better for
datasets with many columns.
Defaults to ``"auto"``.
:type solver: Literal["auto", "irlsm", "l_bfgs", "coordinate_descent_naive", "coordinate_descent",
"gradient_descent_lh", "gradient_descent_sqerr"]
:param alpha: Distribution of regularization between the L1 (Lasso) and L2 (Ridge) penalties. A value of 1 for
alpha represents Lasso regression, a value of 0 produces Ridge regression, and anything in between
specifies the amount of mixing between the two. Default value of alpha is 0 when SOLVER = 'L-BFGS'; 0.5
otherwise.
Defaults to ``None``.
:type alpha: List[float], optional
:param lambda_: Regularization strength
Defaults to ``None``.
:type lambda_: List[float], optional
:param lambda_search: Use lambda search starting at lambda max, given lambda is then interpreted as lambda min
Defaults to ``False``.
:type lambda_search: bool
:param early_stopping: Stop early when there is no more relative improvement on train or validation (if
provided)
Defaults to ``True``.
:type early_stopping: bool
:param nlambdas: Number of lambdas to be used in a search. Default indicates: If alpha is zero, with lambda
search set to True, the value of nlamdas is set to 30 (fewer lambdas are needed for ridge regression)
otherwise it is set to 100.
Defaults to ``-1``.
:type nlambdas: int
:param standardize: Standardize numeric columns to have zero mean and unit variance
Defaults to ``False``.
:type standardize: bool
:param missing_values_handling: Handling of missing values. Either MeanImputation, Skip or PlugValues.
Defaults to ``"mean_imputation"``.
:type missing_values_handling: Literal["mean_imputation", "skip", "plug_values"]
:param plug_values: Plug Values (a single row frame containing values that will be used to impute missing values
of the training/validation frame, use with conjunction missing_values_handling = PlugValues)
Defaults to ``None``.
:type plug_values: Union[None, str, H2OFrame], optional
:param compute_p_values: Request p-values computation, p-values work only with IRLSM solver and no
regularization
Defaults to ``False``.
:type compute_p_values: bool
:param remove_collinear_columns: In case of linearly dependent columns, remove some of the dependent columns
Defaults to ``False``.
:type remove_collinear_columns: bool
:param splines_non_negative: Valid for I-spline (bs=2) only. True if the I-splines are monotonically increasing
(and monotonically non-decreasing) and False if the I-splines are monotonically decreasing (and
monotonically non-increasing). If specified, must be the same size as gam_columns. Values for other
spline types will be ignored. Default to true.
Defaults to ``None``.
:type splines_non_negative: List[bool], optional
:param intercept: Include constant term in the model
Defaults to ``True``.
:type intercept: bool
:param non_negative: Restrict coefficients (not intercept) to be non-negative
Defaults to ``False``.
:type non_negative: bool
:param max_iterations: Maximum number of iterations
Defaults to ``-1``.
:type max_iterations: int
:param objective_epsilon: Converge if objective value changes less than this. Default indicates: If
lambda_search is set to True the value of objective_epsilon is set to .0001. If the lambda_search is set
to False and lambda is equal to zero, the value of objective_epsilon is set to .000001, for any other
value of lambda the default value of objective_epsilon is set to .0001.
Defaults to ``-1.0``.
:type objective_epsilon: float
:param beta_epsilon: Converge if beta changes less (using L-infinity norm) than beta esilon, ONLY applies to
IRLSM solver
Defaults to ``0.0001``.
:type beta_epsilon: float
:param gradient_epsilon: Converge if objective changes less (using L-infinity norm) than this, ONLY applies to
L-BFGS solver. Default indicates: If lambda_search is set to False and lambda is equal to zero, the
default value of gradient_epsilon is equal to .000001, otherwise the default value is .0001. If
lambda_search is set to True, the conditional values above are 1E-8 and 1E-6 respectively.
Defaults to ``-1.0``.
:type gradient_epsilon: float
:param link: Link function.
Defaults to ``"family_default"``.
:type link: Literal["family_default", "identity", "logit", "log", "inverse", "tweedie", "ologit"]
:param startval: double array to initialize coefficients for GAM.
Defaults to ``None``.
:type startval: List[float], optional
:param prior: Prior probability for y==1. To be used only for logistic regression iff the data has been sampled
and the mean of response does not reflect reality.
Defaults to ``-1.0``.
:type prior: float
:param cold_start: Only applicable to multiple alpha/lambda values when calling GLM from GAM. If false, build
the next model for next set of alpha/lambda values starting from the values provided by current model.
If true will start GLM model from scratch.
Defaults to ``False``.
:type cold_start: bool
:param lambda_min_ratio: Minimum lambda used in lambda search, specified as a ratio of lambda_max (the smallest
lambda that drives all coefficients to zero). Default indicates: if the number of observations is greater
than the number of variables, then lambda_min_ratio is set to 0.0001; if the number of observations is
less than the number of variables, then lambda_min_ratio is set to 0.01.
Defaults to ``-1.0``.
:type lambda_min_ratio: float
:param beta_constraints: Beta constraints
Defaults to ``None``.
:type beta_constraints: Union[None, str, H2OFrame], optional
:param max_active_predictors: Maximum number of active predictors during computation. Use as a stopping
criterion to prevent expensive model building with many predictors. Default indicates: If the IRLSM
solver is used, the value of max_active_predictors is set to 5000 otherwise it is set to 100000000.
Defaults to ``-1``.
:type max_active_predictors: int
:param interactions: A list of predictor column indices to interact. All pairwise combinations will be computed
for the list.
Defaults to ``None``.
:type interactions: List[str], optional
:param interaction_pairs: A list of pairwise (first order) column interactions.
Defaults to ``None``.
:type interaction_pairs: List[tuple], optional
:param obj_reg: Likelihood divider in objective value computation, default is 1/nobs
Defaults to ``-1.0``.
:type obj_reg: float
:param export_checkpoints_dir: Automatically export generated models to this directory.
Defaults to ``None``.
:type export_checkpoints_dir: str, optional
:param stopping_rounds: Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0 to disable)
Defaults to ``0``.
:type stopping_rounds: int
:param stopping_metric: Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anomaly_score for Isolation Forest). Note that custom and custom_increasing can only be
used in GBM and DRF with the Python client.
Defaults to ``"auto"``.
:type stopping_metric: Literal["auto", "deviance", "logloss", "mse", "rmse", "mae", "rmsle", "auc", "aucpr", "lift_top_group",
"misclassification", "mean_per_class_error", "custom", "custom_increasing"]
:param stopping_tolerance: Relative tolerance for metric-based stopping criterion (stop if relative improvement
is not at least this much)
Defaults to ``0.001``.
:type stopping_tolerance: float
:param balance_classes: Balance training data class counts via over/under-sampling (for imbalanced data).
Defaults to ``False``.
:type balance_classes: bool
:param class_sampling_factors: Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance during training.
Requires balance_classes.
Defaults to ``None``.
:type class_sampling_factors: List[float], optional
:param max_after_balance_size: Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.
Defaults to ``5.0``.
:type max_after_balance_size: float
:param max_confusion_matrix_size: [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logs
Defaults to ``20``.
:type max_confusion_matrix_size: int
:param max_runtime_secs: Maximum allowed runtime in seconds for model training. Use 0 to disable.
Defaults to ``0.0``.
:type max_runtime_secs: float
:param num_knots: Number of knots for gam predictors. If specified, must specify one for each gam predictor.
For monotone I-splines, mininum = 2, for cs spline, minimum = 3. For thin plate, minimum is size of
polynomial basis + 2.
Defaults to ``None``.
:type num_knots: List[int], optional
:param spline_orders: Order of I-splines or NBSplineTypeI M-splines used for gam predictors. If specified, must
be the same size as gam_columns. For I-splines, the spline_orders will be the same as the polynomials
used to generate the splines. For M-splines, the polynomials used to generate the splines will be
spline_order-1. Values for bs=0 or 1 will be ignored.
Defaults to ``None``.
:type spline_orders: List[int], optional
:param knot_ids: Array storing frame keys of knots. One for each gam column set specified in gam_columns
Defaults to ``None``.
:type knot_ids: List[str], optional
:param gam_columns: Arrays of predictor column names for gam for smoothers using single or multiple predictors
like {{'c1'},{'c2','c3'},{'c4'},...}
Defaults to ``None``.
:type gam_columns: List[List[str]], optional
:param standardize_tp_gam_cols: standardize tp (thin plate) predictor columns
Defaults to ``False``.
:type standardize_tp_gam_cols: bool
:param scale_tp_penalty_mat: Scale penalty matrix for tp (thin plate) smoothers as in R
Defaults to ``False``.
:type scale_tp_penalty_mat: bool
:param bs: Basis function type for each gam predictors, 0 for cr, 1 for thin plate regression with knots, 2 for
monotone I-splines, 3 for NBSplineTypeI M-splines (refer to doc here:
https://github.com/h2oai/h2o-3/issues/6926). If specified, must be the same size as gam_columns
Defaults to ``None``.
:type bs: List[int], optional
:param scale: Smoothing parameter for gam predictors. If specified, must be of the same length as gam_columns
Defaults to ``None``.
:type scale: List[float], optional
:param keep_gam_cols: Save keys of model matrix
Defaults to ``False``.
:type keep_gam_cols: bool
:param store_knot_locations: If set to true, will return knot locations as double[][] array for gam column names
found knots_for_gam. Default to false.
Defaults to ``False``.
:type store_knot_locations: bool
:param auc_type: Set default multinomial AUC type.
Defaults to ``"auto"``.
:type auc_type: Literal["auto", "none", "macro_ovr", "weighted_ovr", "macro_ovo", "weighted_ovo"]
:param gainslift_bins: Gains/Lift table number of bins. 0 means disabled.. Default value -1 means automatic
binning.
Defaults to ``-1``.
:type gainslift_bins: int
"""
super(H2OGeneralizedAdditiveEstimator, self).__init__()
self._parms = {}
self._id = self._parms['model_id'] = model_id
self.training_frame = training_frame
self.validation_frame = validation_frame
self.nfolds = nfolds
self.seed = seed
self.keep_cross_validation_models = keep_cross_validation_models
self.keep_cross_validation_predictions = keep_cross_validation_predictions
self.keep_cross_validation_fold_assignment = keep_cross_validation_fold_assignment
self.fold_assignment = fold_assignment
self.fold_column = fold_column
self.response_column = response_column
self.ignored_columns = ignored_columns
self.ignore_const_cols = ignore_const_cols
self.score_each_iteration = score_each_iteration
self.offset_column = offset_column
self.weights_column = weights_column
self.family = family
self.tweedie_variance_power = tweedie_variance_power
self.tweedie_link_power = tweedie_link_power
self.theta = theta
self.solver = solver
self.alpha = alpha
self.lambda_ = lambda_
self.lambda_search = lambda_search
self.early_stopping = early_stopping
self.nlambdas = nlambdas
self.standardize = standardize
self.missing_values_handling = missing_values_handling
self.plug_values = plug_values
self.compute_p_values = compute_p_values
self.remove_collinear_columns = remove_collinear_columns
self.splines_non_negative = splines_non_negative
self.intercept = intercept
self.non_negative = non_negative
self.max_iterations = max_iterations
self.objective_epsilon = objective_epsilon
self.beta_epsilon = beta_epsilon
self.gradient_epsilon = gradient_epsilon
self.link = link
self.startval = startval
self.prior = prior
self.cold_start = cold_start
self.lambda_min_ratio = lambda_min_ratio
self.beta_constraints = beta_constraints
self.max_active_predictors = max_active_predictors
self.interactions = interactions
self.interaction_pairs = interaction_pairs
self.obj_reg = obj_reg
self.export_checkpoints_dir = export_checkpoints_dir
self.stopping_rounds = stopping_rounds
self.stopping_metric = stopping_metric
self.stopping_tolerance = stopping_tolerance
self.balance_classes = balance_classes
self.class_sampling_factors = class_sampling_factors
self.max_after_balance_size = max_after_balance_size
self.max_confusion_matrix_size = max_confusion_matrix_size
self.max_runtime_secs = max_runtime_secs
self.num_knots = num_knots
self.spline_orders = spline_orders
self.knot_ids = knot_ids
self.gam_columns = gam_columns
self.standardize_tp_gam_cols = standardize_tp_gam_cols
self.scale_tp_penalty_mat = scale_tp_penalty_mat
self.bs = bs
self.scale = scale
self.keep_gam_cols = keep_gam_cols
self.store_knot_locations = store_knot_locations
self.auc_type = auc_type
self.gainslift_bins = gainslift_bins
@property
def training_frame(self):
"""
Id of the training data frame.
Type: ``Union[None, str, H2OFrame]``.
"""
return self._parms.get("training_frame")
@training_frame.setter
def training_frame(self, training_frame):
self._parms["training_frame"] = H2OFrame._validate(training_frame, 'training_frame')
@property
def validation_frame(self):
"""
Id of the validation data frame.
Type: ``Union[None, str, H2OFrame]``.
"""
return self._parms.get("validation_frame")
@validation_frame.setter
def validation_frame(self, validation_frame):
self._parms["validation_frame"] = H2OFrame._validate(validation_frame, 'validation_frame')
@property
def nfolds(self):
"""
Number of folds for K-fold cross-validation (0 to disable or >= 2).
Type: ``int``, defaults to ``0``.
"""
return self._parms.get("nfolds")
@nfolds.setter
def nfolds(self, nfolds):
assert_is_type(nfolds, None, int)
self._parms["nfolds"] = nfolds
@property
def seed(self):
"""
Seed for pseudo random number generator (if applicable)
Type: ``int``, defaults to ``-1``.
"""
return self._parms.get("seed")
@seed.setter
def seed(self, seed):
assert_is_type(seed, None, int)
self._parms["seed"] = seed
@property
def keep_cross_validation_models(self):
"""
Whether to keep the cross-validation models.
Type: ``bool``, defaults to ``True``.
"""
return self._parms.get("keep_cross_validation_models")
@keep_cross_validation_models.setter
def keep_cross_validation_models(self, keep_cross_validation_models):
assert_is_type(keep_cross_validation_models, None, bool)
self._parms["keep_cross_validation_models"] = keep_cross_validation_models
@property
def keep_cross_validation_predictions(self):
"""
Whether to keep the predictions of the cross-validation models.
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("keep_cross_validation_predictions")
@keep_cross_validation_predictions.setter
def keep_cross_validation_predictions(self, keep_cross_validation_predictions):
assert_is_type(keep_cross_validation_predictions, None, bool)
self._parms["keep_cross_validation_predictions"] = keep_cross_validation_predictions
@property
def keep_cross_validation_fold_assignment(self):
"""
Whether to keep the cross-validation fold assignment.
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("keep_cross_validation_fold_assignment")
@keep_cross_validation_fold_assignment.setter
def keep_cross_validation_fold_assignment(self, keep_cross_validation_fold_assignment):
assert_is_type(keep_cross_validation_fold_assignment, None, bool)
self._parms["keep_cross_validation_fold_assignment"] = keep_cross_validation_fold_assignment
@property
def fold_assignment(self):
"""
Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified' option will stratify
the folds based on the response variable, for classification problems.
Type: ``Literal["auto", "random", "modulo", "stratified"]``, defaults to ``"auto"``.
"""
return self._parms.get("fold_assignment")
@fold_assignment.setter
def fold_assignment(self, fold_assignment):
assert_is_type(fold_assignment, None, Enum("auto", "random", "modulo", "stratified"))
self._parms["fold_assignment"] = fold_assignment
@property
def fold_column(self):
"""
Column with cross-validation fold index assignment per observation.
Type: ``str``.
"""
return self._parms.get("fold_column")
@fold_column.setter
def fold_column(self, fold_column):
assert_is_type(fold_column, None, str)
self._parms["fold_column"] = fold_column
@property
def response_column(self):
"""
Response variable column.
Type: ``str``.
"""
return self._parms.get("response_column")
@response_column.setter
def response_column(self, response_column):
assert_is_type(response_column, None, str)
self._parms["response_column"] = response_column
@property
def ignored_columns(self):
"""
Names of columns to ignore for training.
Type: ``List[str]``.
"""
return self._parms.get("ignored_columns")
@ignored_columns.setter
def ignored_columns(self, ignored_columns):
assert_is_type(ignored_columns, None, [str])
self._parms["ignored_columns"] = ignored_columns
@property
def ignore_const_cols(self):
"""
Ignore constant columns.
Type: ``bool``, defaults to ``True``.
"""
return self._parms.get("ignore_const_cols")
@ignore_const_cols.setter
def ignore_const_cols(self, ignore_const_cols):
assert_is_type(ignore_const_cols, None, bool)
self._parms["ignore_const_cols"] = ignore_const_cols
@property
def score_each_iteration(self):
"""
Whether to score during each iteration of model training.
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("score_each_iteration")
@score_each_iteration.setter
def score_each_iteration(self, score_each_iteration):
assert_is_type(score_each_iteration, None, bool)
self._parms["score_each_iteration"] = score_each_iteration
@property
def offset_column(self):
"""
Offset column. This will be added to the combination of columns before applying the link function.
Type: ``str``.
"""
return self._parms.get("offset_column")
@offset_column.setter
def offset_column(self, offset_column):
assert_is_type(offset_column, None, str)
self._parms["offset_column"] = offset_column
@property
def weights_column(self):
"""
Column with observation weights. Giving some observation a weight of zero is equivalent to excluding it from the
dataset; giving an observation a relative weight of 2 is equivalent to repeating that row twice. Negative
weights are not allowed. Note: Weights are per-row observation weights and do not increase the size of the data
frame. This is typically the number of times a row is repeated, but non-integer values are supported as well.
During training, rows with higher weights matter more, due to the larger loss function pre-factor. If you set
weight = 0 for a row, the returned prediction frame at that row is zero and this is incorrect. To get an
accurate prediction, remove all rows with weight == 0.
Type: ``str``.
"""
return self._parms.get("weights_column")
@weights_column.setter
def weights_column(self, weights_column):
assert_is_type(weights_column, None, str)
self._parms["weights_column"] = weights_column
@property
def family(self):
"""
Family. Use binomial for classification with logistic regression, others are for regression problems.
Type: ``Literal["auto", "gaussian", "binomial", "quasibinomial", "ordinal", "multinomial", "poisson", "gamma",
"tweedie", "negativebinomial", "fractionalbinomial"]``, defaults to ``"auto"``.
"""
return self._parms.get("family")
@family.setter
def family(self, family):
assert_is_type(family, None, Enum("auto", "gaussian", "binomial", "quasibinomial", "ordinal", "multinomial", "poisson", "gamma", "tweedie", "negativebinomial", "fractionalbinomial"))
self._parms["family"] = family
@property
def tweedie_variance_power(self):
"""
Tweedie variance power
Type: ``float``, defaults to ``0.0``.
"""
return self._parms.get("tweedie_variance_power")
@tweedie_variance_power.setter
def tweedie_variance_power(self, tweedie_variance_power):
assert_is_type(tweedie_variance_power, None, numeric)
self._parms["tweedie_variance_power"] = tweedie_variance_power
@property
def tweedie_link_power(self):
"""
Tweedie link power
Type: ``float``, defaults to ``0.0``.
"""
return self._parms.get("tweedie_link_power")
@tweedie_link_power.setter
def tweedie_link_power(self, tweedie_link_power):
assert_is_type(tweedie_link_power, None, numeric)
self._parms["tweedie_link_power"] = tweedie_link_power
@property
def theta(self):
"""
Theta
Type: ``float``, defaults to ``0.0``.
"""
return self._parms.get("theta")
@theta.setter
def theta(self, theta):
assert_is_type(theta, None, numeric)
self._parms["theta"] = theta
@property
def solver(self):
"""
AUTO will set the solver based on given data and the other parameters. IRLSM is fast on on problems with small
number of predictors and for lambda-search with L1 penalty, L_BFGS scales better for datasets with many columns.
Type: ``Literal["auto", "irlsm", "l_bfgs", "coordinate_descent_naive", "coordinate_descent",
"gradient_descent_lh", "gradient_descent_sqerr"]``, defaults to ``"auto"``.
"""
return self._parms.get("solver")
@solver.setter
def solver(self, solver):
assert_is_type(solver, None, Enum("auto", "irlsm", "l_bfgs", "coordinate_descent_naive", "coordinate_descent", "gradient_descent_lh", "gradient_descent_sqerr"))
self._parms["solver"] = solver
@property
def alpha(self):
"""
Distribution of regularization between the L1 (Lasso) and L2 (Ridge) penalties. A value of 1 for alpha
represents Lasso regression, a value of 0 produces Ridge regression, and anything in between specifies the
amount of mixing between the two. Default value of alpha is 0 when SOLVER = 'L-BFGS'; 0.5 otherwise.
Type: ``List[float]``.
"""
return self._parms.get("alpha")
@alpha.setter
def alpha(self, alpha):
# For `alpha` and `lambda` the server reports type float[], while in practice simple floats are also ok
assert_is_type(alpha, None, numeric, [numeric])
self._parms["alpha"] = alpha
@property
def lambda_(self):
"""
Regularization strength
Type: ``List[float]``.
"""
return self._parms.get("lambda")
@lambda_.setter
def lambda_(self, lambda_):
assert_is_type(lambda_, None, numeric, [numeric])
self._parms["lambda"] = lambda_
@property
def lambda_search(self):
"""
Use lambda search starting at lambda max, given lambda is then interpreted as lambda min
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("lambda_search")
@lambda_search.setter
def lambda_search(self, lambda_search):
assert_is_type(lambda_search, None, bool)
self._parms["lambda_search"] = lambda_search
@property
def early_stopping(self):
"""
Stop early when there is no more relative improvement on train or validation (if provided)
Type: ``bool``, defaults to ``True``.
"""
return self._parms.get("early_stopping")
@early_stopping.setter
def early_stopping(self, early_stopping):
assert_is_type(early_stopping, None, bool)
self._parms["early_stopping"] = early_stopping
@property
def nlambdas(self):
"""
Number of lambdas to be used in a search. Default indicates: If alpha is zero, with lambda search set to True,
the value of nlamdas is set to 30 (fewer lambdas are needed for ridge regression) otherwise it is set to 100.
Type: ``int``, defaults to ``-1``.
"""
return self._parms.get("nlambdas")
@nlambdas.setter
def nlambdas(self, nlambdas):
assert_is_type(nlambdas, None, int)
self._parms["nlambdas"] = nlambdas
@property
def standardize(self):
"""
Standardize numeric columns to have zero mean and unit variance
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("standardize")
@standardize.setter
def standardize(self, standardize):
assert_is_type(standardize, None, bool)
self._parms["standardize"] = standardize
@property
def missing_values_handling(self):
"""
Handling of missing values. Either MeanImputation, Skip or PlugValues.
Type: ``Literal["mean_imputation", "skip", "plug_values"]``, defaults to ``"mean_imputation"``.
"""
return self._parms.get("missing_values_handling")
@missing_values_handling.setter
def missing_values_handling(self, missing_values_handling):
assert_is_type(missing_values_handling, None, Enum("mean_imputation", "skip", "plug_values"))
self._parms["missing_values_handling"] = missing_values_handling
@property
def plug_values(self):
"""
Plug Values (a single row frame containing values that will be used to impute missing values of the
training/validation frame, use with conjunction missing_values_handling = PlugValues)
Type: ``Union[None, str, H2OFrame]``.
"""
return self._parms.get("plug_values")
@plug_values.setter
def plug_values(self, plug_values):
self._parms["plug_values"] = H2OFrame._validate(plug_values, 'plug_values')
@property
def compute_p_values(self):
"""
Request p-values computation, p-values work only with IRLSM solver and no regularization
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("compute_p_values")
@compute_p_values.setter
def compute_p_values(self, compute_p_values):
assert_is_type(compute_p_values, None, bool)
self._parms["compute_p_values"] = compute_p_values
@property
def remove_collinear_columns(self):
"""
In case of linearly dependent columns, remove some of the dependent columns
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("remove_collinear_columns")
@remove_collinear_columns.setter
def remove_collinear_columns(self, remove_collinear_columns):
assert_is_type(remove_collinear_columns, None, bool)
self._parms["remove_collinear_columns"] = remove_collinear_columns
@property
def splines_non_negative(self):
"""
Valid for I-spline (bs=2) only. True if the I-splines are monotonically increasing (and monotonically non-
decreasing) and False if the I-splines are monotonically decreasing (and monotonically non-increasing). If
specified, must be the same size as gam_columns. Values for other spline types will be ignored. Default to
true.
Type: ``List[bool]``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/binomial_20_cols_10KRows.csv")
>>> y = "C21"
>>> x = ["C19","C20"]
>>> numKnots = [5,5,5]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='gaussian',
... gam_columns=["C16","C17","C18"],
... bs=[2,2,2],
... splines_non_negative=[True, True, True])
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o_model.coef()
"""
return self._parms.get("splines_non_negative")
@splines_non_negative.setter
def splines_non_negative(self, splines_non_negative):
assert_is_type(splines_non_negative, None, [bool])
self._parms["splines_non_negative"] = splines_non_negative
@property
def intercept(self):
"""
Include constant term in the model
Type: ``bool``, defaults to ``True``.
"""
return self._parms.get("intercept")
@intercept.setter
def intercept(self, intercept):
assert_is_type(intercept, None, bool)
self._parms["intercept"] = intercept
@property
def non_negative(self):
"""
Restrict coefficients (not intercept) to be non-negative
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("non_negative")
@non_negative.setter
def non_negative(self, non_negative):
assert_is_type(non_negative, None, bool)
self._parms["non_negative"] = non_negative
@property
def max_iterations(self):
"""
Maximum number of iterations
Type: ``int``, defaults to ``-1``.
"""
return self._parms.get("max_iterations")
@max_iterations.setter
def max_iterations(self, max_iterations):
assert_is_type(max_iterations, None, int)
self._parms["max_iterations"] = max_iterations
@property
def objective_epsilon(self):
"""
Converge if objective value changes less than this. Default indicates: If lambda_search is set to True the
value of objective_epsilon is set to .0001. If the lambda_search is set to False and lambda is equal to zero,
the value of objective_epsilon is set to .000001, for any other value of lambda the default value of
objective_epsilon is set to .0001.
Type: ``float``, defaults to ``-1.0``.
"""
return self._parms.get("objective_epsilon")
@objective_epsilon.setter
def objective_epsilon(self, objective_epsilon):
assert_is_type(objective_epsilon, None, numeric)
self._parms["objective_epsilon"] = objective_epsilon
@property
def beta_epsilon(self):
"""
Converge if beta changes less (using L-infinity norm) than beta esilon, ONLY applies to IRLSM solver
Type: ``float``, defaults to ``0.0001``.
"""
return self._parms.get("beta_epsilon")
@beta_epsilon.setter
def beta_epsilon(self, beta_epsilon):
assert_is_type(beta_epsilon, None, numeric)
self._parms["beta_epsilon"] = beta_epsilon
@property
def gradient_epsilon(self):
"""
Converge if objective changes less (using L-infinity norm) than this, ONLY applies to L-BFGS solver. Default
indicates: If lambda_search is set to False and lambda is equal to zero, the default value of gradient_epsilon
is equal to .000001, otherwise the default value is .0001. If lambda_search is set to True, the conditional
values above are 1E-8 and 1E-6 respectively.
Type: ``float``, defaults to ``-1.0``.
"""
return self._parms.get("gradient_epsilon")
@gradient_epsilon.setter
def gradient_epsilon(self, gradient_epsilon):
assert_is_type(gradient_epsilon, None, numeric)
self._parms["gradient_epsilon"] = gradient_epsilon
@property
def link(self):
"""
Link function.
Type: ``Literal["family_default", "identity", "logit", "log", "inverse", "tweedie", "ologit"]``, defaults to
``"family_default"``.
"""
return self._parms.get("link")
@link.setter
def link(self, link):
assert_is_type(link, None, Enum("family_default", "identity", "logit", "log", "inverse", "tweedie", "ologit"))
self._parms["link"] = link
@property
def startval(self):
"""
double array to initialize coefficients for GAM.
Type: ``List[float]``.
"""
return self._parms.get("startval")
@startval.setter
def startval(self, startval):
assert_is_type(startval, None, [numeric])
self._parms["startval"] = startval
@property
def prior(self):
"""
Prior probability for y==1. To be used only for logistic regression iff the data has been sampled and the mean
of response does not reflect reality.
Type: ``float``, defaults to ``-1.0``.
"""
return self._parms.get("prior")
@prior.setter
def prior(self, prior):
assert_is_type(prior, None, numeric)
self._parms["prior"] = prior
@property
def cold_start(self):
"""
Only applicable to multiple alpha/lambda values when calling GLM from GAM. If false, build the next model for
next set of alpha/lambda values starting from the values provided by current model. If true will start GLM
model from scratch.
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("cold_start")
@cold_start.setter
def cold_start(self, cold_start):
assert_is_type(cold_start, None, bool)
self._parms["cold_start"] = cold_start
@property
def lambda_min_ratio(self):
"""
Minimum lambda used in lambda search, specified as a ratio of lambda_max (the smallest lambda that drives all
coefficients to zero). Default indicates: if the number of observations is greater than the number of variables,
then lambda_min_ratio is set to 0.0001; if the number of observations is less than the number of variables, then
lambda_min_ratio is set to 0.01.
Type: ``float``, defaults to ``-1.0``.
"""
return self._parms.get("lambda_min_ratio")
@lambda_min_ratio.setter
def lambda_min_ratio(self, lambda_min_ratio):
assert_is_type(lambda_min_ratio, None, numeric)
self._parms["lambda_min_ratio"] = lambda_min_ratio
@property
def beta_constraints(self):
"""
Beta constraints
Type: ``Union[None, str, H2OFrame]``.
"""
return self._parms.get("beta_constraints")
@beta_constraints.setter
def beta_constraints(self, beta_constraints):
self._parms["beta_constraints"] = H2OFrame._validate(beta_constraints, 'beta_constraints')
@property
def max_active_predictors(self):
"""
Maximum number of active predictors during computation. Use as a stopping criterion to prevent expensive model
building with many predictors. Default indicates: If the IRLSM solver is used, the value of
max_active_predictors is set to 5000 otherwise it is set to 100000000.
Type: ``int``, defaults to ``-1``.
"""
return self._parms.get("max_active_predictors")
@max_active_predictors.setter
def max_active_predictors(self, max_active_predictors):
assert_is_type(max_active_predictors, None, int)
self._parms["max_active_predictors"] = max_active_predictors
@property
def interactions(self):
"""
A list of predictor column indices to interact. All pairwise combinations will be computed for the list.
Type: ``List[str]``.
"""
return self._parms.get("interactions")
@interactions.setter
def interactions(self, interactions):
assert_is_type(interactions, None, [str])
self._parms["interactions"] = interactions
@property
def interaction_pairs(self):
"""
A list of pairwise (first order) column interactions.
Type: ``List[tuple]``.
"""
return self._parms.get("interaction_pairs")
@interaction_pairs.setter
def interaction_pairs(self, interaction_pairs):
assert_is_type(interaction_pairs, None, [tuple])
self._parms["interaction_pairs"] = interaction_pairs
@property
def obj_reg(self):
"""
Likelihood divider in objective value computation, default is 1/nobs
Type: ``float``, defaults to ``-1.0``.
"""
return self._parms.get("obj_reg")
@obj_reg.setter
def obj_reg(self, obj_reg):
assert_is_type(obj_reg, None, numeric)
self._parms["obj_reg"] = obj_reg
@property
def export_checkpoints_dir(self):
"""
Automatically export generated models to this directory.
Type: ``str``.
"""
return self._parms.get("export_checkpoints_dir")
@export_checkpoints_dir.setter
def export_checkpoints_dir(self, export_checkpoints_dir):
assert_is_type(export_checkpoints_dir, None, str)
self._parms["export_checkpoints_dir"] = export_checkpoints_dir
@property
def stopping_rounds(self):
"""
Early stopping based on convergence of stopping_metric. Stop if simple moving average of length k of the
stopping_metric does not improve for k:=stopping_rounds scoring events (0 to disable)
Type: ``int``, defaults to ``0``.
"""
return self._parms.get("stopping_rounds")
@stopping_rounds.setter
def stopping_rounds(self, stopping_rounds):
assert_is_type(stopping_rounds, None, int)
self._parms["stopping_rounds"] = stopping_rounds
@property
def stopping_metric(self):
"""
Metric to use for early stopping (AUTO: logloss for classification, deviance for regression and anomaly_score
for Isolation Forest). Note that custom and custom_increasing can only be used in GBM and DRF with the Python
client.
Type: ``Literal["auto", "deviance", "logloss", "mse", "rmse", "mae", "rmsle", "auc", "aucpr", "lift_top_group",
"misclassification", "mean_per_class_error", "custom", "custom_increasing"]``, defaults to ``"auto"``.
"""
return self._parms.get("stopping_metric")
@stopping_metric.setter
def stopping_metric(self, stopping_metric):
assert_is_type(stopping_metric, None, Enum("auto", "deviance", "logloss", "mse", "rmse", "mae", "rmsle", "auc", "aucpr", "lift_top_group", "misclassification", "mean_per_class_error", "custom", "custom_increasing"))
self._parms["stopping_metric"] = stopping_metric
@property
def stopping_tolerance(self):
"""
Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much)
Type: ``float``, defaults to ``0.001``.
"""
return self._parms.get("stopping_tolerance")
@stopping_tolerance.setter
def stopping_tolerance(self, stopping_tolerance):
assert_is_type(stopping_tolerance, None, numeric)
self._parms["stopping_tolerance"] = stopping_tolerance
@property
def balance_classes(self):
"""
Balance training data class counts via over/under-sampling (for imbalanced data).
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("balance_classes")
@balance_classes.setter
def balance_classes(self, balance_classes):
assert_is_type(balance_classes, None, bool)
self._parms["balance_classes"] = balance_classes
@property
def class_sampling_factors(self):
"""
Desired over/under-sampling ratios per class (in lexicographic order). If not specified, sampling factors will
be automatically computed to obtain class balance during training. Requires balance_classes.
Type: ``List[float]``.
"""
return self._parms.get("class_sampling_factors")
@class_sampling_factors.setter
def class_sampling_factors(self, class_sampling_factors):
assert_is_type(class_sampling_factors, None, [float])
self._parms["class_sampling_factors"] = class_sampling_factors
@property
def max_after_balance_size(self):
"""
Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires
balance_classes.
Type: ``float``, defaults to ``5.0``.
"""
return self._parms.get("max_after_balance_size")
@max_after_balance_size.setter
def max_after_balance_size(self, max_after_balance_size):
assert_is_type(max_after_balance_size, None, float)
self._parms["max_after_balance_size"] = max_after_balance_size
@property
def max_confusion_matrix_size(self):
"""
[Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs
Type: ``int``, defaults to ``20``.
"""
return self._parms.get("max_confusion_matrix_size")
@max_confusion_matrix_size.setter
def max_confusion_matrix_size(self, max_confusion_matrix_size):
assert_is_type(max_confusion_matrix_size, None, int)
self._parms["max_confusion_matrix_size"] = max_confusion_matrix_size
@property
def max_runtime_secs(self):
"""
Maximum allowed runtime in seconds for model training. Use 0 to disable.
Type: ``float``, defaults to ``0.0``.
"""
return self._parms.get("max_runtime_secs")
@max_runtime_secs.setter
def max_runtime_secs(self, max_runtime_secs):
assert_is_type(max_runtime_secs, None, numeric)
self._parms["max_runtime_secs"] = max_runtime_secs
@property
def num_knots(self):
"""
Number of knots for gam predictors. If specified, must specify one for each gam predictor. For monotone
I-splines, mininum = 2, for cs spline, minimum = 3. For thin plate, minimum is size of polynomial basis + 2.
Type: ``List[int]``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/multinomial_10_classes_10_cols_10000_Rows_train.csv")
>>> h2o_data["C11"] = h2o_data["C11"].asfactor()
>>> train, test = h2o_data.split_frame(ratios = [.8])
>>> y = "C11"
>>> x = ["C9","C10"]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='multinomial',
... store_knot_locations=True,
... gam_columns=["C6","C7","C8"],
... num_knots=[3,4,5])
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o_model.get_knot_locations()
"""
return self._parms.get("num_knots")
@num_knots.setter
def num_knots(self, num_knots):
assert_is_type(num_knots, None, [int])
self._parms["num_knots"] = num_knots
@property
def spline_orders(self):
"""
Order of I-splines or NBSplineTypeI M-splines used for gam predictors. If specified, must be the same size as
gam_columns. For I-splines, the spline_orders will be the same as the polynomials used to generate the splines.
For M-splines, the polynomials used to generate the splines will be spline_order-1. Values for bs=0 or 1 will
be ignored.
Type: ``List[int]``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/binomial_20_cols_10KRows.csv")
>>> y = "C21"
>>> x = ["C19","C20"]
>>> numKnots = [5,5,5]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='gaussian',
... gam_columns=["C16","C17","C18"],
... bs=[2,2,2],
... spline_orders=[3,4,5])
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o_model.coef()
"""
return self._parms.get("spline_orders")
@spline_orders.setter
def spline_orders(self, spline_orders):
assert_is_type(spline_orders, None, [int])
self._parms["spline_orders"] = spline_orders
@property
def knot_ids(self):
"""
Array storing frame keys of knots. One for each gam column set specified in gam_columns
Type: ``List[str]``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> knots1 = [-1.99905699, -0.98143075, 0.02599159, 1.00770987, 1.99942290]
>>> frameKnots1 = h2o.H2OFrame(python_obj=knots1)
>>> knots2 = [-1.999821861, -1.005257990, -0.006716042, 1.002197392, 1.999073589]
>>> frameKnots2 = h2o.H2OFrame(python_obj=knots2)
>>> knots3 = [-1.999675688, -0.979893796, 0.007573327, 1.011437347, 1.999611676]
>>> frameKnots3 = h2o.H2OFrame(python_obj=knots3)
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/multinomial_10_classes_10_cols_10000_Rows_train.csv")()
>>> h2o_data["C11"] = h2o_data["C11"].asfactor()
>>> train, test = h2o_data.split_frame(ratios = [.8])
>>> y = "C11"
>>> x = ["C9","C10"]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='multinomial',
... gam_columns=["C6","C7","C8"],
... store_knot_locations=True,
... knot_ids=[frameKnots1.key, frameKnots2.key, frameKnots3.key])
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o_model.get_knot_locations()
"""
return self._parms.get("knot_ids")
@knot_ids.setter
def knot_ids(self, knot_ids):
assert_is_type(knot_ids, None, [str])
self._parms["knot_ids"] = knot_ids
@property
def gam_columns(self):
"""
Arrays of predictor column names for gam for smoothers using single or multiple predictors like
{{'c1'},{'c2','c3'},{'c4'},...}
Type: ``List[List[str]]``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/multinomial_10_classes_10_cols_10000_Rows_train.csv")
>>> h2o_data["C11"] = h2o_data["C11"].asfactor()
>>> y = "C11"
>>> x = ["C9","C10"]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='multinomial',
... gam_columns=["C6","C7","C8"])
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o_model.coef()
"""
return self._parms.get("gam_columns")
@gam_columns.setter
def gam_columns(self, gam_columns):
assert_is_type(gam_columns, None, [U(str, [str])])
if gam_columns: # standardize as a nested list
gam_columns = [[g] if isinstance(g, str) else g for g in gam_columns]
self._parms["gam_columns"] = gam_columns
@property
def standardize_tp_gam_cols(self):
"""
standardize tp (thin plate) predictor columns
Type: ``bool``, defaults to ``False``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/binomial_20_cols_10KRows.csv")
>>> y = "C21"
>>> x = ["C19","C20"]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='gaussian',
... gam_columns=["C16","C17","C18"],
... bs=[1,1,1],
... standardize_tp_gam_cols=True)
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o_model.coef()
"""
return self._parms.get("standardize_tp_gam_cols")
@standardize_tp_gam_cols.setter
def standardize_tp_gam_cols(self, standardize_tp_gam_cols):
assert_is_type(standardize_tp_gam_cols, None, bool)
self._parms["standardize_tp_gam_cols"] = standardize_tp_gam_cols
@property
def scale_tp_penalty_mat(self):
"""
Scale penalty matrix for tp (thin plate) smoothers as in R
Type: ``bool``, defaults to ``False``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/multinomial_10_classes_10_cols_10000_Rows_train.cs
>>> h2o_data["C11"] = h2o_data["C11"].asfactor()
>>> y = "C11"
>>> x = ["C9","C10"]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='multinomial',
... scale_tp_penalty_mat=True,
... gam_columns=["C6","C7","C8"],
... bs=[1,1,1])
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o_model.coef()
"""
return self._parms.get("scale_tp_penalty_mat")
@scale_tp_penalty_mat.setter
def scale_tp_penalty_mat(self, scale_tp_penalty_mat):
assert_is_type(scale_tp_penalty_mat, None, bool)
self._parms["scale_tp_penalty_mat"] = scale_tp_penalty_mat
@property
def bs(self):
"""
Basis function type for each gam predictors, 0 for cr, 1 for thin plate regression with knots, 2 for monotone
I-splines, 3 for NBSplineTypeI M-splines (refer to doc here: https://github.com/h2oai/h2o-3/issues/6926). If
specified, must be the same size as gam_columns
Type: ``List[int]``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/multinomial_10_classes_10_cols_10000_Rows_train.csv")
>>> h2o_data["C11"] = h2o_data["C11"].asfactor()
>>> y = "C11"
>>> x = ["C9","C10"]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='multinomial',
... gam_columns=["C6","C7","C8"],
... bs=[0,1,3])
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o_model.coef() # note the spline type in the names of gam column coefficients
"""
return self._parms.get("bs")
@bs.setter
def bs(self, bs):
assert_is_type(bs, None, [int])
self._parms["bs"] = bs
@property
def scale(self):
"""
Smoothing parameter for gam predictors. If specified, must be of the same length as gam_columns
Type: ``List[float]``.
"""
return self._parms.get("scale")
@scale.setter
def scale(self, scale):
assert_is_type(scale, None, [numeric])
self._parms["scale"] = scale
@property
def keep_gam_cols(self):
"""
Save keys of model matrix
Type: ``bool``, defaults to ``False``.
:examples:
>>> import h2o
>>> from h2o.estimators.gam import H2OGeneralizedAdditiveEstimator
>>> h2o.init()
>>> h2o_data = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/multinomial_10_classes_10_cols_10000_Rows_train.csv")
>>> h2o_data["C11"] = h2o_data["C11"].asfactor()
>>> train, test = h2o_data.split_frame(ratios = [.8])
>>> y = "C11"
>>> x = ["C9","C10"]
>>> h2o_model = H2OGeneralizedAdditiveEstimator(family='multinomial',
... keep_gam_cols=True,
... gam_columns=["C6","C7","C8"])
>>> h2o_model.train(x=x, y=y, training_frame=h2o_data)
>>> h2o.get_frame(h2o_model._model_json["output"] ["gam_transformed_center_key"])
"""
return self._parms.get("keep_gam_cols")
@keep_gam_cols.setter
def keep_gam_cols(self, keep_gam_cols):
assert_is_type(keep_gam_cols, None, bool)
self._parms["keep_gam_cols"] = keep_gam_cols
@property
def store_knot_locations(self):
"""
If set to true, will return knot locations as double[][] array for gam column names found knots_for_gam.
Default to false.
Type: ``bool``, defaults to ``False``.
"""
return self._parms.get("store_knot_locations")
@store_knot_locations.setter
def store_knot_locations(self, store_knot_locations):
assert_is_type(store_knot_locations, None, bool)
self._parms["store_knot_locations"] = store_knot_locations
@property
def auc_type(self):
"""
Set default multinomial AUC type.
Type: ``Literal["auto", "none", "macro_ovr", "weighted_ovr", "macro_ovo", "weighted_ovo"]``, defaults to
``"auto"``.
"""
return self._parms.get("auc_type")
@auc_type.setter
def auc_type(self, auc_type):
assert_is_type(auc_type, None, Enum("auto", "none", "macro_ovr", "weighted_ovr", "macro_ovo", "weighted_ovo"))
self._parms["auc_type"] = auc_type
@property
def gainslift_bins(self):
"""
Gains/Lift table number of bins. 0 means disabled.. Default value -1 means automatic binning.
Type: ``int``, defaults to ``-1``.
"""
return self._parms.get("gainslift_bins")
@gainslift_bins.setter
def gainslift_bins(self, gainslift_bins):
assert_is_type(gainslift_bins, None, int)
self._parms["gainslift_bins"] = gainslift_bins
Lambda = deprecated_property('Lambda', lambda_)
def _additional_used_columns(self, parms):
"""
:return: Gam columns if specified.
"""
return parms["gam_columns"]
def _summary(self):
"""Return a detailed summary of the model."""
model = self._model_json["output"]
if "glm_model_summary" in model and model["glm_model_summary"] is not None:
return model["glm_model_summary"]
[docs] def scoring_history(self):
"""
Retrieve Model Score History.
:returns: The score history as an H2OTwoDimTable or a Pandas DataFrame.
"""
model = self._model_json["output"]
if "glm_scoring_history" in model and model["glm_scoring_history"] is not None:
return model["glm_scoring_history"].as_data_frame()
print("No score history for this model")
[docs] def get_knot_locations(self, gam_column=None):
"""
Retrieve gam columns knot locations if store_knot_locations parameter is enabled. If a gam column name is
specified, the know loations corresponding to that gam column is returned. Otherwise, all knot locations are
returned for all gam columns. The order of the gam columns are specified in gam_knot_column_names of the
model output.
:return: knot locations of gam columns.
"""
if not(self.actual_params["store_knot_locations"]):
raise H2OValueError("Knot locations are not available. Please re-run with store_knot_locations=True")
knot_locations = self._model_json['output']['knot_locations']
gam_names = self._model_json['output']['gam_knot_column_names']
if gam_column is None:
return knot_locations
else:
if gam_column in gam_names:
return knot_locations[gam_names.index(gam_column)]
else:
raise H2OValueError("{0} is not a valid gam column name.".format(gam_column))
[docs] def get_gam_knot_column_names(self):
"""
Retrieve gam column names corresponding to the knot locations that will be returned if store_knot_locations
parameter is enabled.
:return: gam column names whose knot locations are stored in the knot_locations.
"""
if not(self.actual_params["store_knot_locations"]):
raise H2OValueError("Knot locations are not available. Please re-run with store_knot_locations=True")
return self._model_json['output']['gam_knot_column_names']